© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82735
    Prev
    Next
    INDEX
    Explanations

    code, software, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on structured identifiers and version‐style tokens (e.g. series/edition labels, book numbers, API version numbers, and other numeric IDs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *-*-
    -1.02
    UBLIC
    -1.00
    ଶ
    -0.98
    liai
    -0.96
     maneu
    -0.94
    Abraço
    -0.94
    Também
    -0.93
     ~~~
    -0.91
    andeep
    -0.89
    ________,
    -0.89
    POSITIVE LOGITS
     مؤرشف
    1.30
    consulté
    1.12
     を
    1.10
    ::~
    1.09
    ActionPerformed
    1.02
    脚注
    1.02
     said
    0.97
    springframework
    0.96
     Affiliations
    0.96
     wikipagina
    0.95
    Activations Density 0.162%

    No Known Activations